knitr::opts_chunk$set(echo = TRUE, message = FALSE, warning = FALSE)
library(tidyverse)
library(here)
library(sf)
library(tmap)
cmd-shift-enter: shortcut for running the current code chunk
cmd-option-i: shortcut for creating a code chunk
sf_trees <- read_csv(here("data", "sf_trees", "sf_trees.csv"),
show_col_types = FALSE) # hides information about column types that usually pops up under code chunk
# In console:
# view(sf_trees) to view dataset
# names(sf_trees) will give names of each column
# summary(sf_trees) gives summary of min, max, mean, etc of each column <- quick rundown of values
Example 1: Find counts of observations by ‘legal_status’ & wrangle a bit.
### Method 1: group_by %>% summarize()
sf_trees %>%
group_by(legal_status) %>%
summarize(tree_count = n()) # n() counts how many rows there are in the data frame
## # A tibble: 10 × 2
## legal_status tree_count
## <chr> <int>
## 1 DPW Maintained 141725
## 2 Landmark tree 42
## 3 Permitted Site 39732
## 4 Planning Code 138.1 required 971
## 5 Private 163
## 6 Property Tree 316
## 7 Section 143 230
## 8 Significant Tree 1648
## 9 Undocumented 8106
## 10 <NA> 54
### Method 2: different way, plus a few new funcitons
top_five_status <- sf_trees %>%
count(legal_status) %>%
drop_na(legal_status) %>% # will drop any row with an 'NA' in it in the legal_status column
rename(tree_count = n) %>%
relocate(tree_count) %>% # relocates tree_count to the front of the columns
slice_max(tree_count, n = 5) %>% # takes only maximum up to 5
arrange(desc(tree_count)) # arrange by tree_count in descending order
ggplot(data = top_five_status, aes(x = fct_reorder(legal_status, tree_count), y = tree_count)) +
geom_col(fill = 'darkgreen') +
labs(x = 'Legal Status',
y = 'Tree Count') +
coord_flip() +
theme_minimal()
# use 'fct_reorder() to reoder 'legal_status' by 'tree_count' and order by factor (from smallest to largest) ** Note: you can use '-' infront of 'tree_count' to switch order to go from highest to lowest
Example 2 Only going to keep observations where legal status is “Permitted Site” and caretaker is “MTA”, and store as permitted_data_df
shift-cmd-c to commen/uncomment quickly
# sf_trees$legal_status %>% unique() # takes legal status column and gets rid of duplicates to see what the unique values are
# unique(sf_trees$caretaker)
permitted_data_df <- sf_trees %>%
filter(legal_status == 'Permitted Site', caretaker == 'MTA')
# Note: '|' between 'Permitted Site' and 'caretaker' means 'or', so if legal status is 'Permitted Site' OR caretaker is 'MTA', or both then it should appear in the data table. EX) filter(legal_status == 'Permitted Site' | caretaker == 'MTA')
#Note: if you want to filter for multiple legal statuses use %in% and `c()` EX) filter(legal_status %in% c('Permitted Site', 'Private'), caretaker == 'MTA')
Example 3: Only keep Blackwood Acacia trees, and then only keep columns legal status, date, latitude, longitude, and store as blackwood_acacia_df
blackwood_acacia_df <- sf_trees %>%
filter(str_detect(species, 'Blackwood Acacia')) %>% # in this column, keep any rows where you find 'Blackwood Acacia'
select(legal_status, date, lat = latitude, lon = longitude)
### Make a little graph of locations
ggplot(data = blackwood_acacia_df, aes(x = lon, y = lat)) +
geom_point(color = 'darkgreen')
Example 4 Use tidyr::separate() to separate one column into multiple columns
sf_trees_sep <- sf_trees %>%
separate(species, into = c("species_scientific", "species_common"), sep = "::") # separate 'species' column into two columns at the '::'
Example 5 use tidyr::unite() to combine columns
ex_5 <- sf_trees %>%
unite('id_status', tree_id, legal_status, sep = '_CHECK_THIS_OUT')
# Note: also drops the old columns and only retains the new column, 'id_status'
Step 1 Convert lat/lon to spatial points, st_as_sf() this takes spatial temporal data and convert to sf object (a bunch of spatial points)
blackwood_acacia_sf <- blackwood_acacia_df %>%
drop_na(lat, lon) %>%
st_as_sf(coords = c('lon', 'lat')) # R now knows that this is a spatial object (see geometry colun that has appeared!)
### we need to tell R what the coordinate reference system is using `st_crs()`
st_crs(blackwood_acacia_sf) <- 4326 # this is the epsg number for a reference system
ggplot(data = blackwood_acacia_sf) + # dont put in any aesthetics because geom_sf already knows the aesthetics
geom_sf(color = 'darkgreen') +
theme_minimal()
sf_map <- read_sf(here('data', 'sf_map', 'tl_2017_06075_roads.shp'))
sf_map_transform <- st_transform(sf_map, 4326) # need to make sure the reference is the same for this map as the blackwood_acacia_sf (4326)
ggplot(data = sf_map_transform) +
geom_sf()
Combine the maps!!
ggplot() +
geom_sf(data = sf_map,
size = 0.1,
color = 'darkgrey') +
geom_sf(data = blackwood_acacia_sf,
color = 'red',
size = 0.5) +
theme_void() +
labs(title = 'Blackwood acacias in SF')
# Note: order in which geom_sf() appear is the order of the layers. So your bottom layer should be written first.
tmap_mode('view') # sets up map to be interactive
tm_shape(blackwood_acacia_sf) + # equivalent of ggplot()
tm_dots() # equivalent to geom_point()